Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add benskamps/career-compass-mcp --skill career-compassgit clone --depth 1 https://github.com/benskamps/career-compass-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/benskamps/career-compass-mcp/career-compass)<a href="https://agentmods.dev/skills/benskamps/career-compass-mcp/career-compass"><img src="https://agentmods.dev/badge/skills/benskamps/career-compass-mcp/career-compass/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/benskamps/career-compass-mcp/career-compass"><img src="https://agentmods.dev/badge/skills/benskamps/career-compass-mcp/career-compass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00153 | $0.06081 |
| Opus 5.5 | $0.00061 | $0.02432 |
| Sonnet 5.5 | $0.00031 | $0.01216 |
| Haiku 4.5 | $0.00015 | $0.00608 |
Grade A, and why
career-compass scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with Career Compass
Career Compass is an MCP server that stores the user's career history (the Career KB) and job pipeline as YAML on their own disk. Its tools read from that KB, so answers get sharper as the KB fills in. But the user installed this to get help with their job search today, not to fill in a database. Deliver something useful in the first reply, then offer to save it.
First, which mode are you in?
Tools available (Claude Code, or Cowork on the user's computer): use them as described below.
Tools not available. There are two cases. Tell them apart only by what the user says, not by what you can see of your own environment: most people without the tools are in claude.ai chat. A terminal, files, a memory folder or a failed file read are not the user saying anything; don't mention the helper, Node.js or setup because of them.
- claude.ai chat (web, desktop, or mobile): the default whenever the user hasn't said they are in Claude Code or Cowork. This is a full mode, not a fallback. Do the task directly from what the user pastes or attaches, using the method under "Doing the work without the tools", and carry their search from chat to chat with the Career Compass card (below). Don't apologize for missing tools, and never mention Node.js, servers, installs or setup. Say once, in a clause, that in Claude Code or Cowork on their computer Career Compass also remembers their history and tracks applications for them; it is an option, never a requirement.
- Claude Code or Cowork, but the server didn't start: only when the user says they are
there. Still do the task from what they pasted. Say once, briefly, that Career Compass's
local helper didn't start, so this session won't be remembered, and that
node --version(it needs 22 or newer) checks the most common cause. Don't tell them to use Claude Code or Cowork: they are already there.
Either way, don't repeat the note in later replies, and never present your own work as a tool's output.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed b62c79cd53a8
- 2d ago Changed · +82 lines · +11 tokens per session scan B → A c1c0947a1e1f
- 3d ago Changed · +14 lines · +41 tokens per session 642b8ea2eea2
- 4d ago Changed · +118 lines scan A → B a0eaf86b8526
- 5d ago Changed 546212764982
- 7d ago Changed · +44 lines · +26 tokens per session 2985cf085351
- 8d ago Changed · +43 lines · +19 tokens per session f9237fa3afef
- 14d ago First seen · 61 lines · 56 tokens per session scan A e9bfa7fefbee
career-compass is a skill published in the GitHub repository benskamps/career-compass-mcp (6 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 6,081 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
Other skills, from other repositories
kochab
Kochab, a personalized resume-based job-search assistant that runs a recurring scan and everything downstream of it. Use when the user wants to start or run a job search, shares a resume, or says "set up my job scan," "find roles that fit my resume," or "what should I apply to." Also use to tailor a resume, draft a…
interviewing
Use when the user gets an interview invitation, moves into an interview process, wants to track interview stages, capture post-interview notes, draft follow-up messages, or update an application to interviewing.
get-started
Use when the user is new to Job Hunt Skills and wants to see what it does or set up their workspace — including "I'm new to Job Hunt Skills", "help me get started", "set me up", "first time using this", "here's my resume, tailor it for this job", "can you look at my resume", pasting a resume and a job posting…
yc-job-tracker
Track and filter YC startup job listings for AI/ML engineering roles. Builds a daily-refreshed local database of relevant jobs with scoring and alerts for new postings.
Job Description Analyzer
Analyze job postings, calculate match scores, identify gaps, and create application strategy.
opportunity-brief
Research a company and a specific role, then produce an honest brief on whether it is worth pursuing. Use this whenever the user mentions a recruiter reaching out, a job posting they found, a company someone told them about, or a role they are weighing. Triggers on "a recruiter contacted me," "should I apply to,"…